In order to explore the relationship of control and initiative to discourse processes like centering, we analyze the distribution of four different classes of anaphora for two data sets.
Trang 1Mixed Initiative in Dialogue: An Investigation into Discourse
Segmentation
Marilyn Walker University of Pennsylvania*
Computer Science Dept
Philadelphia, PA 19104 lyn@linc.cis.upenn.edu
Steve Whittaker Hewlett Packard Laboratories Bristol, England BS12 6QZ
HP Stanford Science Center sjw@hplb.hpl.hp.com
A b s t r a c t
Conversation between two people is usually of
MIXED-INITIATIVE, with CONTROL over the con-
versation being transferred from one person to an-
other We apply a set of rules for the transfer of
control to 4 sets of dialogues consisting of a total of
1862 turns The application of the control rules lets
us derive domain-independent discourse structures
The derived structures indicate that initiative plays
a role in the structuring of discourse In order to
explore the relationship of control and initiative to
discourse processes like centering, we analyze the
distribution of four different classes of anaphora for
two data sets This distribution indicates that some
control segments are hierarchically related to oth-
ers The analysis suggests that discourse partic-
ipants often mutually agree to a change of topic
We also compared initiative in Task Oriented and
Advice Giving dialogues and found that both allo-
cation of control and the manner in which control
is transferred is radically different for the two dia-
logue types These differences can be explained in
terms of collaborative planning principles
1 I n t r o d u c t i o n
Conversation between two people has a number of
characteristics that have yet to be modeled ade-
quately in human-computer dialogue Conversa-
tion is BIDIRECTIONAL; there is a two way flow
of information between participants Information
*This research was partially funded by ARO grants
DAAG29-84-K-0061 and DAAL03-89-C0031PRI, DARPA
grant N00014-85-K0018, and NSF grant MCS-82-19196 at
the University of Pennsylvania, and by Hewlett Packard,
U.K
is exchanged by MIXED-INITIATIVE Each partici- pant will, on occasion, take the conversational lead Conversational partners not only respond to what others say, but feel free to volunteer information that is not requested and sometimes ask questions
of their own[Nic76] As INITIATIVE passes back and forth between the discourse participants, we say that CONTROL over the conversation gets trans- ferred from one discourse participant to another Why should we, as computational linguists, be interested in factors that contribute to the interac- tivity of a discourse? There are both theoretical and practical motivations First, we wish to ex- tend formal accounts of single utterances produced
by single speakers to explain multi-participant, multi-utterance discourses[Po186, CP86] Previ- ous studies of the discourse structure of multi- participant dialogues have often factored out the role of MIXED-INITIATIVE, by allocating control to one participant[Gro77, Coh84], or by assuming a passive listener[McK85, Coh87] Since conversation
is a collaborative process[CWG86, SSJ74], models
of conversation can provide the basis for extending planning theories[GS90, CLNO90] When the sit- uation requires the negotiation of a collaborative plan, these theories must account for the interact- ing beliefs and intentions of multiple participants
~,From a practical perspective, there is ample evi- dence that limited mixed-initiative has contributed
to lack of system usability Many researchers have noted that the absence of mixed-initiative gives rise to two problems with expert systems: They don't allow users to participate in the rea- soning process, or to ask the questions they want answered[PHW82, Kid85, FL89] In addition, ques- tion answering systems often fail to take account
of the system's role as a conversational partner
Trang 2For example, fragmentary utterances may be inter-
preted with respect to the previous user input, but
what users say is often in reaction to the system's
previous response[CP82, Sid83]
In this paper we focus on interactive discourse
We model mixed-initiative using an utterance type
classification and a set of rules for transfer of control
between discourse participants t h a t were proposed
by Whittaker and Stenton[WS88] We evaluate the
generality of this analysis by applying the control
rules to 4 sets of dialogues, including b o t h advi-
sory dialogues (ADs) and task-oriented dialogues
(TODs) We analysed both financial and support
ADs The financial ADs are from the radio talk
show "Harry Gross: Speaking of Your Money "1
The support ADs resulted from a client phoning
an expert to help them diagnose and repair various
software faults ~ T h e TODs are a b o u t the construc-
tion of a plastic water pump in both telephone and
keyboard modality S
The application of the control rules to these dia-
logues lets us derive domain-independent discourse
segments with each segment being controlled by one
or other discourse participant We propose that
control segments correspond to different subgoals
in the evolving discourse plan In addition, we ar-
gue that various linguistic devices are necessary for
conversational participants to coordinate their con-
tributions to the dialogue and agree on their mu-
tual beliefs with respect to a evolving plan, for ex-
ample, to agree that a particular subgoal has been
achieved A final phenomenon concerns shifts of
control and the devices used to achieve this Con-
trol shifts occur because it is unusual for a single
participant to be responsible for coordinating the
achievement of the whole discourse plan When a
different participant assumes control of a discourse
subgoal then a control shift occurs and the par-
ticipants must have mechanisms for achieving this
T h e control framework distinguishes instances in
which a control shift is negotiated by the partic-
ipants and instances where one participant seizes
control
This paper has two objectives:
110 randomly selected dialogues (474 turns) from a corpus
t h a t was collected a n d transcribed by M a r t h a Pollack a n d
Julia Hirschberg[HL87, PHW82]
24 dialogues (450 turns) from tapes m a d e a t one of
Hewlett-Packard's customer response centers See [WS88]
35 keyboard (224 turns) a n d 5 telephone dialogues (714
turns), which were collected in a n experiment by Phil Cohen
to explore the relationship between modality, interactivity
a n d use of referring expressions[Coh84]
To explore the phenomenon of control in rela- tion to ATTENTIONAL STATE [GS86, GJW86, Sid79] 4 We predict shifts of attentional state when shifts in control are negotiated and agreed by all participants, but not when con- trol is seized by one participant without the acceptance of the others This should be re- flected in different distribution of anaphora in the two cases
To test predictions about the distribution of control in different types of dialogues Be- cause the T O D ' s embody the master-slave assumption[GSg0], and control is allocated to the expert, our expectation is that control should be located exclusively with one partici- pant in the T O D s in contrast with the ADs
2 R u l e s for t h e A l l o c a t i o n
a n d T r a n s f e r o f C o n t r o l
We use the framework for the allocation and trans- fer of control of Whittaker and Stenton[WS88] The analysis is based on a classification of utterances into 4 types 5 These are:
• U T T E R A N C E T Y P E S
to state facts Yes and No in response to
a question were classified as assertions on the basis that they are supplying informa- tion
stigate action Generally imperative form, b u t could be indirect such as M y suggestion would be that you do
-QUESTIONS: Utterances which are in- tended to elicit information, including in- direct forms such as I was wondering
w h e t h e r I should
PROMPTS: Utterances which did not ex- press propositional content, such as Yeah, Okay, Uh-huh
4The theory of centering, which is part of attentional state, depends on discourse participants' recognizing the be- ginning and end of a discourse segment[BFP87, Wal89] 5The relationship between utterance level meaning and discourse intentions rests on a theory of joint commitment
or shared plans[GSg0, CLNO90, LCN90]
71
Trang 3Note that prompts are in direct contrast to the
other options that a participant has available at
any point in the discourse By indicating t h a t the
speaker does not want the floor, prompts function
on a number of levels, including the expression of
understanding or agreement[Sch82]
The rules for the allocation of control are based
on the utterance type classification and allow a di-
alogue to be divided into segments t h a t correspond
to which speaker is the controller of the segment
• C O N T R O L R U L E S
U T T E R A N C E
A S S E R T I O N
C O M M A N D
Q U E S T I O N
P R O M P T
C O N T R O L L E R (ICP)
S P E A K E R , unless response
to a Question
S P E A K E R
S P E A K E R , unless response
to Question or C o m m a n d
H E A R E R
The definition of controller can be seen to cor-
respond to the intuitions behind the term INITI-
ATING CONVERSATIONAL PARTICIPANT (ICP), who
is defined as the initiator of a given discourse
segment[GS86] The OTHER CONVERSATIONAL
PARTICIPANT(S), OCP, m a y speak some utterances
in a segment, but the DISCOURSE SEGMENT PUR-
POSE, must be the purpose of the ICP The control
rules place a segment b o u n d a r y whenever the roles
of the participants (ICP or O C P ) change For ex-
ample:
Abdication Example
E: "And they are, in your gen youql find that they've relo-
Cated into the labelled common area"
(ASSERT - E control)
C: "That's right." (PROMPT - E control)
E: "Yeah" (PROMPT - E abdicates control)
CONTROL SHIFT TO C - -
C: "I've got two in there There are two of them." (ASSERT
- C control)
E: "Right" (PROMPT - C control)
C: "And there's another one which is % RESA"
(ASSERT - C control)
E: "OK urn" (PROMPT - C control)
C: "VS" (ASSERT- C control)
E: "Right" (PROMPT - C control)
C: "Mm" (PROMPT - C abdicates control)
CONTROL SHIFT TO E - - - -
E: "Right and you haven't got - I assume you haven't got
local labelled common with those labels"
(QUESTION - E control)
Whittaker and Stenton also performed a post-hoe
analysis of the segment boundaries t h a t are defined
by the control rules The boundaries fell into one
of three types:
• C O N T R O L S H I F T T Y P E S
- ABDICATION: Okay, go on
- REPETITION/SUMMARY: That would be
my recommendation and that will ensure that you get a logically integral set of files
- N E R P T I O : It is something new though urn
ABDICATIONS 6 correspond to those cases where the controller produces a prompt as the last utterance of the segment The class REPETI- TION/SUMMARY corresponds to the controller pro- ducing a r e d u n d a n t utterance The utterance is either an exact repetition of previous propositional content, or a s u m m a r y that realizes a proposition,
P , which could have been inferred from what came before Thus orderly control shifts occur when the controller explicitly indicates that s/he wishes
to relinquish control W h a t unifies ABDICATIONS and REPETITION/SUMMARIES is that the controller supplies no new propositional content The re- maining class, INTERRUPTIONS, characterize shifts occurring when the noncontroller displays initia- tive by seizing control This class is more general than other definitions of Interruptions It prop- erly contains cross-speaker interruptions that in- volve topic shift, similar to the true-interruptions
of Grosz and Sidner[GS86], as well as clarification subdialogues[Sid83, LA90]
This classification suggests that the transfer of control is often a collaborative phenomenon Since
a noncontroller(OCP), has the option of seizing con- trol at any juncture in discourse, it would seem that controllers(ICPs), are in control because the noncontroller allows it These observations address problems raised by Grosz and Sidner, namely how ICPs signal and O C P s recognize segment bound- aries The claim is that shifts of control often do not occur until the controller indicates the end of
a discourse segment by abdicating or producing a repetition/summary
A n a p h o r a
To determine the relationship between the de- rived control segments and ATTENTIONAL STATE we 6Our abdication category was called prompt by [WS88]
Trang 4looked at the distribution of anaphora with respect
to the control segments in the ADs All d a t a were
analysed statistically by X 2 and all differences cited
are significant at the 0.05 level We looked at all
anaphors (excluding first and second person), and
grouped t h e m into 4 classes
• C l a s s e s o f A n a p h o r s
- 3RD PERSON: it, they, them, their, she,
he, her, him, his
- ONE/SOME, one of them, one of those, a
new one, that one, the other one, some
- DEICTIC: Noun phrases, e.g this, that,
this NP, that NP, those NP, these N P
- EVENT: Verb Phrases, Sentences, Seg-
ments, e.g this, that, it
The class DEICTIC refers to deictic references to
material introduced by noun phrases, whereas the
class EVENT refers to material introduced clausally
3.1 Hierarchical R e l a t i o n s h i p s
The first phenomenon we noted was that the
anaphora distribution indicated t h a t some seg-
ments are hierarchically related to others 7 This
was especially apparent in cases where one dis-
course participant interrupted briefly, then imme-
diately passed control back to the other
Interrupt/Abdicate 1
A: the only way I could do that was to take a to take a
one third down and to take back a mortgage (ASSERTION)
-INTERRUPT SHIFT TO B - - -
2 B: When you talk about one third put a number on it
(QUESTION)
3 A: uh 15 thou (ASSERTION, but response)
4 B: go ahead (PROMPT)
- - - - A B D I C A T E SHIFT BACK TO 4.-
5 A: and then I'm a mortgage baz.k for 36
The following example illustrates the same point
Interrupt/Abdicate 2
1 A: The maximum amount will be $400 on THEIR
tax return (ASSERTION)
INTERRUPT SHIFT TO B
7Similar phenomena has been noted by many researchers
in discourse including[Gro77, Hob79, Sid79, PHg0]
2 B: 400 for the whole year? (QUESTION)
3 A: yeah it'll be 20% (ASSERTION, but response)
4 B: um hm (PROMPT)
- - - A B D I C A T E SHIFT BACK TO A-
5 A: now if indeed THEY pay the $2000 to your wife
T h e control segments as defined would treat both
of these cases as composed of 3 different segments But this ignores the fact that utterances (1) and (5) have closely related propositional content in the first example, and t h a t the plural pronoun straddles the central subsegment with the same referents be- ing picked out by they and their in the second ex- ample Thus we allowed for hierarchical segments
by treating the interruptions of 2-4 as subsegments, and utterances 1 and 5 as related parts of the parent segments All interruptions were treated as embed- dings in this way However the relationship of the segment after the interruption to the segment be- fore must be determined on independent grounds such as topic or intentional structure
3.2 D i s t r i b u t i o n
Once we extended the control framework to allow for the embedding of interrupts, we coded every anaphor with respect to whether its antecedent lay outside or within the current segment These are la- belled X (cross segment b o u n d a r y antecedent) NX (no cross segment boundary), in Figure 1 In addi- tion we break these down as to which type of control shift occurred at the previous segment boundary
3rd Pets One Deictic Event
x xlxk xlxi x x I
Abdication 1 105 0 10 27 7 18
3 ll01 4 l i 3 1 5 li 5 i Inter pt 7 :7 il 0 I 0 il 8 I 9 i l 2 1, I
TOTAL 11 165 el 0 I 14 ii 24 I 41 el '1 34 i
Figure 1: Distribution of A n a p h o r a in Finance ADs
We also looked at the distribution of anaphora in the Support ADs and found similar results
For both dialogues, the distribution of anaphors varies according to which type of control shift oc- curred at the previous segment boundary When
we look at the different types of anaphora, we find
t h a t third person and one anaphors cross bound-
73
Trang 5Abdication
S u m m a r y
Interrupt
T O T A L
3rd Pets One Deictic Event
16 11211 1 11 11191 23 Ills 42 I
Figure 2: Distribution of Anaphora in Support ADs
aries extremely rarely, but the event anaphors and
the deictic pronouns demonstrate a different pat-
tern What does this mean?
The fact that anaphora is more likely to cross
segment boundaries following interruptions than for
summaries or abdications is consistent with the con-
trol principles With both summaries and abdica-
tions the speaker gives an explicit signal t h a t s / h e
wishes to relinquish control In contrast, interrup-
tions are the u n p r o m p t e d a t t e m p t s of the listener
to seize control, often having to do with some 'prob-
lem' with the controller's utterance Therefore, in-
terruptions are much more likely to be within topic
But why should deixis and event anaphors be-
have differently from the other anaphors? Deixis
serves to pick out objects t h a t cannot be selected
by the use of standard anaphora, i.e we should
expect the referents for deixis to be outside imme-
diate focus and hence more likely to be outside the
current segment[Web86] T h e picture is more com-
plex for event anaphora, which seems to serve a
number of different functions in the dialogue It is
used to talk about the past events t h a t lead up to
the current situation, I did T H A T in order to move
the place It is also used to refer to sets of propo-
sitions of the preceding discourse, Now T H A T ' S a
little background (cf [Web88]) T h e most prevalent
usei however, was to refer to future events or ac-
tions, T H A T would be the move that I would make
- but you have to do I T the same day
SUMMARY EXAMPLE
A: As far as you are concerned THAT could cost you more
what's your tax bracket? (QUESTION)
B: Well I'm on pension Harry and my wife hasn't worked at
all and (ASSERT/RESP)
A: No reason at all why you can't do THAT (ASSERTION)
- - - S U M M A R Y 3HIFT to B
13: See my comment was if we should throw even the $2000
into an IRA or something for her (ASSERTION)
REPETITION SHIFT to A
A: You could do T H A T too ( A S S E R T I O N )
Since the task in the ADs is to develop a plan, speakers use event anaphora as concise references to the plans they have just negotiated and to discuss the status and quality of plans that have been sug- gested Thus the frequent cross-speaker references
to future events and actions correspond to phases of plan negotiation[PHW82] More importantly these references are closely related to the control struc- ture The example above illustrates the clustering
of event anaphora at segment boundaries One dis- course participant uses an anaphor to summarize a plan, but when the other participant evaluates this plan there may be a control shift and any reference
to the plan will necessarily cross a control boundary
T h e distribution of event anaphora bears this out, since 23/25 references to future actions are within
2 utterances of a segment boundary (See the ex- ample above) More significantly every instance of event anaphora crossing a segment boundary occurs when the speaker is talking about future events or actions
We also looked at the T O D s for instances of anaphora being used to describe a future act in the way that we observed in the ADs However, over the 938 turns in the TODs, there were only 18 instances of event anaphora, because in the main there were few occasions when it was necessary to talk about the plan The financial ADs had 45 event anaphors in 474 utterances
4 C o n t r o l a n d C o l l a b o r a t i v e
P l a n s
To explore the relationship of control to planning,
we compare the TODs with both types of ADs (financial and support) We would expect these dialogues to differ in terms of initiative In the ADs, the objective is to develop a collaborative plan through a series of conversational exchanges Both discourse participants believe that the expert has knowledge about the domain, but only has partial information about the situation T h e y also believe
t h a t the advisee must contribute both the prob- lem description and also constraints as to how the problem can be solved This information must be exchanged, so that the mutual beliefs necessary to develop the collaborative plan are established in the conversation[Jos82] The situation is different
Trang 6in the T O D s Both participants here believe at
the outset t h a t the expert has sufficient informa-
tion a b o u t the situation and complete and correct
knowledge a b o u t how to execute the Task Since
the apprentice has no need to assert information
to change the e x p e r t ' s beliefs or to ask questions
to verify the e x p e r t ' s beliefs or to issue commands,
we should not expect the apprentice to have con-
trol S / h e is merely present to execute the actions
indicated by the knowledgeable participant
T h e differences in the beliefs and knowledge
states of the participants can be interpreted in the
terms of the collaborative planning principles of
W h i t t a k e r and Stenton[WS88] We generalize the
principles of INFORMATION QUALITY and PLAN
QUALITY, which predict when an interrupt should
o c c u r
• INFORMATION QUALITY: T h e listener m u s t be-
lieve t h a t the information t h a t the speaker has
provided is true, unambiguous and relevant to
the m u t u a l goal This corresponds to the two
rules: (A1) TRUTH: If the listener believes a
fact P and believes t h a t fact to be relevant and
either believes t h a t the speaker believes not P
or t h a t the speaker does not know P then inter-
rupt; (A2)AMBIGUITY: If the listener believes
t h a t the speaker's assertion is relevant but am-
biguous then interrupt
• PLAN QUALITY: T h e listener must believe t h a t
the action proposed by the speaker is a p a r t of
an adequate plan to achieve the m u t u a l goal
and the action must also be comprehensible to
the listener T h e two rules to express this are:
(B1)EFFECTIVENESS: If the listener believes
P and either believes t h a t P presents an ob-
stacle to the proposed plan or believes t h a t P
• is p a r t of the proposed plan t h a t has already
been satisfied, then interrupt; (B2) AMBIGU-
ITY: I f the listener believes t h a t an assertion
a b o u t the proposed plan is ambiguous, then
interrupt
These principles indirectly proyide a means to
ensure mutual belief Since a participant m u s t in-
t e r r u p t if any condition for an interrupt holds, then
lack of interruption signals t h a t there is no discrep-
ancy in m u t u a l beliefs If there is such a discrep-
ancy, the interruption is a necessary contribution
to a collaborative plan, not a distraction from the
joint activity
We compare ADs to T O D s with respect to how
T u r n s / S e g
E x p - C o n t r
A b d i c a t i o n
S u m m a r y Interrupt
Finance Support Task-Phone Task-Key 7.49 8.03 15.68 11.27
Turns/Seg: Average number of turns between control shifts Exp-Contr: % total turns controlled by expert
Abdication: ~ control shifts that are Abdications
Summaries: % control shifts that are Reps/Summaries
Interrupt: ~ control shifts that are Interrupts Figure 3: Differences in Control for Dialogue T y p e s
often control is exchanged by calculating the aver- age n u m b e r of turns between control shifts s We also investigate whether control is shared equally between participants and what percentage of con- trol shifts are represented by abdications, inter- rupts, and summaries for each dialogue type See Figure 3
Three things are striking a b o u t this data As we predicted, the distribution of control between ex-
p e r t and client is completely different in the ADs and the T O D s T h e expert has control for around 90% of utterances in the T O D s whereas control is shared almost equally in the ADs Secondly, con-
t r a r y to our expectations, we did find some in- stances of shifts in the T O D s Thirdly, the distri- bution of interruptions and summaries differs across dialogue types How can the collaborative planning principles highlight the differences we observe?
There seem to be two reasons why shifts occur in the T O D s First, m a n y interruptions in the T O D s result from the apprentice seizing control just to indicate t h a t there is a t e m p o r a r y p r o b l e m and t h a t plan execution should be delayed
TASK INTERRUPT 1, A is the Instructor A: It's hard to get on (ASSERTION)
- - - I N T E R R U P T SHIFT TO B B: Not there yet - ouch yep it's there (ASSERTION) A: Okay (PROMPT)
B: Yeah (PROMPT) -ABDICATE SHIFT TO A - - A: All right Now there's a little blue cap
Second, control was exchanged when the execu- tion of the task s t a r t e d to go awry
8 We e x c l u d e d t u r n s in dialogue o p e n i n g s a n d closings
75
Trang 7T A S K I N T E R R U P T 2, A is t h e I n s t r u c t o r
A: A n d t h e n t h e elbow goes over t h a t t h e big e n d of the
elbow ( C O M M A N D )
- - - I N T E R R U P T S H I F T T O B ~
B: You said t h a t it d i d n ' t fit tight, b u t it d o e s n ' t fit t i g h t at
all, okay ( A S S E R T I O N )
A: Okay ( P R O M P T )
B: Let m e t r y THIS - oo1~ - a g a i n ( A S S E R T I O N )
T h e problem with the physical situation indicates
to the apprentice that the relevant beliefs are no
longer shared T h e Instructor is not in possession
of critical information such as the current state of
the apprentice's pump This necessitates an infor-
mation exchange to resynchronize mutual beliefs,
so t h a t the rest of the plan "~ ~,v be successfully ex-
ecuted However, since control is explicitly allo-
cated t o t h e instructor in TODs, there is no reason
for that participant to believe that the other has
any contribution to make Thus there are fewer
a t t e m p t s by the instructor to coordinate activity,
such as by using summaries to synchronize mutual
beliefs Therefore, if the apprentice needs to make
a contribution, s/he must do so via interruption,
explaining why there are many more interruptions
in these dialogues 9 In addition, the majority of
Interruptions (73%) are initiated by apprentices, in
contrast to the ADs in which only 29% are produced
by t h e Clients
Summaries are more frequent in ADs In the ADs
both participants believe t h a t a plan cannot be con-
structed without contributions from both of them
Abdications and summaries are devices which al-
low these contributions to be coordinated and par-
ticipants use these devices to explicitly set up op-
portunities for one another to make a contribution,
and to ensure mutual bellefs The increased fre-
quency of summaries in the ADs may result from
the fact t h a t the participants start with discrepant
mutual beliefs about the situation and that estab-
lishing and maintaining mutual beliefs is a key part
of the ADs
5 D i s c u s s i o n
It has Often been stated that discourse is an inher-
ently collaborative process and that this is man-
ifested in certain phenomena, e.g the use of
9 T h e higher, p e r c e n t a g e o f I n t e r r u p t i o n s in t h e k e y b o a r d
T O D s i n c o m p a r i s o n w i t h t h e t ~1 ~ /.hone T O D s parallels Ovi-
a t t a n d C o h e n ' s analysis, showing t h a t p a r t i c i p a n t s exploit
t h e Wider b a n d w i d t h of t h e iptoractive s p o k e n channel to
b r e a k tasks d o w n into s u b t a s k s t C o h 8 4 , OC89]
anaphora and cue words [GS86, HL87, Coh87] by which the speaker makes aspects of the discourse structure explicit We found shifts of attentional state when shifts in control are negotiated and agreed by all participants, but not when control
is seized by one participant without the acceptance
of the others This was reflected in different distri- bution of anaphora in the two cases Furthermore
we found that not all types of anaphora behaved
in the same way Event anaphora clustered at seg- ment boundaries when it was used to refer to pre- ceding segments and was more likely to cross seg- ment boundaries because of its function in talking about the proposed plan We also found that con- trol was distributed and exchanged differently in the ADs and TODs These results provide support for the control rules
In our analysis we argued for hierarchical orga- nization of the control segments on the basis of specific examples of interruptions We also be- lieve that there are other levels of structure in dis- course t h a t are not captured by the control rules, e.g control shifts do not always correspond with task boundaries T h e r e can be topic shifts with- out change of initiation, change of control without
a topic shift[WS88] T h e relationship of cue words, intonational contour[PH90] and the use of modal subordination[Rob86] to the segments derived from the control rules is a topic for future research
A more controversial question concerns rhetori- cal relations and the extent to which these are de- tected and used by listeners[GS86] Hobbs has ap- plied COHERENCE RELATIONS to face-to-face con- versation in which mixed-initiative is displayed by participants[HA85, Hob79] One category o f rhetor- ical relation he describes is t h a t of ELABORATION,
in which a speaker repeats the propositional con- tent of a previous utterance Hobbs has some diffi- culties determining the function of this repetition, but we maintain t h a t the function follows from the more general principles of the control rules: speak- ers signal that they wish to shift control by sup- plying no new propositional content Abdications, repetitions and summaries all add no new informa- tion and function to signal to the listener that the speaker has nothing further to say right now The listener certainly must recognize this fact
Summaries appear to have an additional function
of synchronization, by allowing both participants to agree on what propositions are mutually believed
at that point in the discussion Thus this work highlights aspects of collaboration in discourse, but
Trang 8should be formally integrated with research on
collaborative planning[GS90, LCN90], particularly
with respect to the relation between control shifts
and the coordination o f plans
6 A c k n o w l e d g e m e n t s
We would like to thank Aravind Joshi for his sup-
port, comments and criticisms Discussions of joint
action with Phil Cohen and the members of CSLI's
DIA working group have influenced the first au-
thor We are also indebted to Susan Brennan, Herb
Clark, Julia Hirschberg, Jerry Hobbs, Libby Levi-
son, Kathy McKeown, Ellen Prince, Penni Sibun,
Candy Sidner, Martha Pollack, Phil Stenton, and
Bonnie Webber for their insightful comments and
criticisms on drafts of this paper
R e f e r e n c e s
Friedman, and Carl J Pollard A cen-
155-162, 1987
[CLNO90] Phillip R Cohen, Hector J Levesque,
Jose H T Nunes, and Sharon L Ovi-
att Task oriented dialogue as a conse-
quence of joint activity, 1990 Unpub-
lished Manuscript
ferring and the modality of communica-
146, 1984
[Coh87] Robin Cohen Analyzing the structure
rault, and James F Allen 1982 Beyond
question answering In Wendy Lehnert
245-274 Lawrence Erlbaum Ass Inc,
Hillsdale, N.J., 1982
[CWG86]
[FL89]
[GJW86]
[Gro77]
[GS86]
[GS90]
[HA85]
[HL87]
[Hob79]
[Jos82]
Lynn Webber Barbara J Grosz, Karen
440 Morgan Kauffman, Los Altos, Ca.,
1986
Herbert H Clark and Deanna Wilkes- Gibbs Referring as a collaborative pro-
David M Frohlich and Paul Luff Con- versational resources for situated action
puter Human Interaction of the ACM,
1989
Barbara J Grosz, Aravind K Joshi, and Scott Weinstein Towards a computa- tional theory of discourse interpretation Unpublished Manuscript, 1986
Barbara J Grosz The representation and use of focus in dialogue understand- ing Technical Report 151, SRI Inter- national, 333 Ravenswood Ave, Menlo Park, Ca 94025, 1977
Barbara J Grosz and Candace L Sid-
Barbara J Grosz and Candace L Sid-
Morgan and Pollack, eds Intentions
in Communication, MIT Press, Cam-
Jerry R Hobbs and Michael H Agar The coherence of incoherent discourse Technical Report CSLI-85-38, Center for the Study of Language and Informa- tion, Ventura Hall, Stanford University, Stanford, CA 94305, 1985
Julia Hirschberg and Diane Litman Now lets talk about now: Identifying
171, Stanford University, Stanford, Ca.,
1987
Jerry R Hobbs Coherence and corefer-
77
Trang 9[Kid85]
[LA90]
[LCN90]
[McK85]
[Nic76]
[oc89]
[PH90]
[PHW82]
[Po186]
Smith eds Mutual Knowledge, Aca-
demic Press, New York, New York,
pages 181-199, 1982
of an expert system In P Johnson
puters: Designing the Interface Cam-
bridge University Press, Cambridge,
U.K., 1985
Diane Litman and James Allen Rec-
ognizing and relating discourse inten-
hen, Morgan and Pollack, eds Inten-
tions in Communication, MIT Press,
Cambridge, MA., 1990
Hector J Levesque, Phillip R Cohen,
and Jose H T Nunes On acting to-
strategies for generating natural lan-
27(1):1-42, September 1985
R.S Nickerson On converational in-
teraction with computers In SiegFried
Interactive Graphics Systems, pages
101-65 Elsevier Science, 1976
Sharon L Oviatt and Philip R Cohen
The effects of interaction on spoken dis-
the ACL, pages 126-134, 1989
bert and Julia Hirschberg The meaning
of intonational contours in the interpre-
and Pollack, eds Intentions in Commu-
nication, MIT Press, Cambridge, MA.,
1990
Martha Pollack, Julia Hirschberg, and
Bonnie Webber User participation in
the reasoning process of expert systems
In Proc National Conference on Artifi-
cial Intelligence, 1982
Martha Pollack Inferring domain plans
in question answering Technical Report
403, SRI International - Artificial Intel-
ligence Center, 1986
[Rob86]
[Sch82]
[Sid79]
[Sid83]
[SSJ74]
[Wa189]
[Web86]
[Web88]
[ws88]
and Anaphora PhD thesis, Linguis- tics Dept, University of Massachusetts, Amherst, 1986
Emanuel A Sehegloff Discourse as an interactional achievement: Some uses of 'uh huh' and other things that come between sentences In D Tannen, ed-
Talk, pages 71-93 Georgetown Univer-
sity Press, 1982
Candace L Sidner Toward a computa- tional theory of definite anaphora com- prehension in english Technical Report AI-TR-537, MIT, 1979
means: the recognition of speakers plans
Computers and Mathematics, 9:71-82,
1983
Harvey Sacks, Emmanuel Schegloff, and Gail Jefferson A simplest systematics for the organization of turn-taking in
1974
27th Annual Meeting of the A CL, pages
251-261, 1989
Bonnie Lynn Webber Two steps closer
to event reference Technical Report MS-CIS-86-74, Line Lab 42, Depart- ment of Computer and Information Sci- ence, University of Pennsylvania, 1986 Bonnie Lynn Webber Discourse deixis:
Proc 26th Annual Meeting of the ACL, Association of Computational Linguis- tics, pages 113-123, 1988
Steve Whittaker and Phil Stenton Cues and control in expert client dialogues In
Proc 26th Annual Meeting of the ACL, Association of Computational Linguis- tics, pages 123-130, 1988